© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 86976
    Prev
    Next
    INDEX
    Explanations

    Bell X UH aircraft designs

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on technical alphanumeric designations—model numbers, engine codes, acronyms, and similar uppercase‐and‐numeric tags.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ธอ
    -0.85
     préc
    -0.83
     세트
    -0.81
     Metode
    -0.78
    ρίες
    -0.76
     Villanueva
    -0.75
     حرفه
    -0.75
     automobili
    -0.75
    ственных
    -0.74
     thoại
    -0.73
    POSITIVE LOGITS
     demonstr
    1.15
     Joint
    0.88
     demonstrators
    0.88
     Project
    0.84
     pola
    0.83
     Collaborative
    0.82
    Joint
    0.81
     contenders
    0.80
     future
    0.79
     proposed
    0.79
    Activations Density 0.043%

    No Known Activations